refactor: remove build sub-coordinator, flatten create-expert pipeline

definitions/create-expert/perstack.toml

@@ -1,13 +1,12 @@
 # =============================================================================
 # Delegation Tree
 #
-# create-expert                        — pipeline orchestration (plan → build)
-# ├── @create-expert/plan              — requirements + architecture → plan.md
-# └── @create-expert/build             — write → review → test → verify cycle
-#     ├── @create-expert/write-definition — perstack.toml authoring
-#     ├── @create-expert/review-definition — plan alignment review (soft gate)
-#     ├── @create-expert/test-expert      — single query execution (pure executor, no evaluation)
-#     └── @create-expert/verify-test      — hard signal execution + reproducibility + structural checks
+# create-expert                          — plan → write → review → test → verify
+# ├── @create-expert/plan                — requirements + architecture → plan.md
+# ├── @create-expert/write-definition    — perstack.toml authoring
+# ├── @create-expert/review-definition   — plan alignment review (soft gate)
+# ├── @create-expert/test-expert         — single query execution (pure executor, no evaluation)
+# └── @create-expert/verify-test         — hard signal execution + reproducibility + structural checks
 # =============================================================================
 #
 # =============================================================================
@@ -37,7 +36,7 @@
 #      value here because plan alignment is semantic, not syntactic.
 #    - Structural correctness (delegates array, pick list, exec capability)
 #      is enforced by hard signals in verify-test.
-#    - Build loop has two gates: review (soft) must pass before testing,
+#    - Coordinator runs two gates: review (soft) must pass before testing,
 #      verify (hard) must pass before completion.
 #
 # 3. Domain Agnosticism
@@ -89,7 +88,7 @@
 
 [experts."create-expert"]
 defaultModelTier = "high"
-version = "1.0.20"
+version = "1.0.21"
 description = "Creates and modifies Perstack expert definitions in perstack.toml"
 instruction = """
 You are the coordinator for creating and modifying Perstack expert definitions. perstack.toml is the single source of truth — your job is to produce or modify it according to the user's request.
@@ -101,24 +100,47 @@ You are the coordinator for creating and modifying Perstack expert definitions.
 
 ## Delegates
 
-- @create-expert/plan — requirements analysis + architecture design: use cases, verification signals, domain knowledge, delegation tree
-- @create-expert/build — write → review → test → verify cycle (internally delegates to write-definition, review-definition, test-expert, verify-test)
+- @create-expert/plan — requirements analysis + architecture design
+- @create-expert/write-definition — writes or modifies perstack.toml from plan.md
+- @create-expert/review-definition — reviews perstack.toml against plan.md for domain alignment and instruction quality
+- @create-expert/test-expert — executes the test query against perstack.toml and reports what happened (no evaluation)
+- @create-expert/verify-test — executes hard signal checks, verifies their reproducibility, and checks the definition structure
 
 ## Coordination
 
 1. Delete stale plan.md from previous runs
 2. Determine Create or Update mode
 3. Delegate to plan: user's request + mode (+ perstack.toml path if Update)
-4. Delegate to build: plan.md path (+ perstack.toml path if Update). Build handles the full write → test → verify → improve cycle internally.
-5. Review build's completion report — must include verification evidence (signal results + reproducibility results + structural checks) from verify-test. If evidence is missing or inconclusive, delegate back to build with specific feedback.
-6. If plan.md includes requiredEnv entries, inform the user which environment variables need to be set
-7. attemptCompletion with summary + verification evidence from build
+4. Run the write → review → test → verify cycle (see below)
+5. If plan.md includes requiredEnv entries, inform the user which environment variables need to be set
+6. attemptCompletion with summary + verification evidence
+
+## Write → Review → Test → Verify Cycle
+
+1. Delegate to write-definition: pass plan.md path (and existing perstack.toml path if Update mode)
+2. Delegate to review-definition: pass plan.md path and perstack.toml path
+3. If review returns CONTINUE: delegate to write-definition with the review feedback, then restart from step 2
+4. If review returns PASS: delegate to test-expert with the test query from plan.md, perstack.toml path, and coordinator expert name (do NOT pass verification signals — test-expert is a pure executor)
+5. Delegate to verify-test: pass the test-expert result, the verification signals from plan.md, and the perstack.toml path
+6. If verify-test returns CONTINUE: validate the feedback — only hard signal failures (command X → expected Y → got Z) are valid loop reasons. If the feedback is not tied to a specific command result, do NOT loop. Delegate to write-definition with actionable feedback, restart from step 2
+7. If verify-test returns PASS: cycle complete
 
-The only deliverable is perstack.toml. Intermediate files (plan.md) may be cleaned up, but perstack.toml must never be deleted.
+### Maximum 3 iterations
+The cycle may run at most 3 times. If all must signals have not passed after 3 iterations, report what passed, what failed, and the feedback from each iteration. Do NOT continue looping.
+
+### One delegate call per response
+Delegate to exactly ONE delegate per response. Do NOT include multiple delegations in a single response.
+
+### Guardrails
+- Do NOT delete perstack.toml — it is the final deliverable
+- The only deliverable is perstack.toml. Intermediate files (plan.md) may be cleaned up, but perstack.toml must never be deleted.
 """
 delegates = [
   "@create-expert/plan",
-  "@create-expert/build",
+  "@create-expert/write-definition",
+  "@create-expert/review-definition",
+  "@create-expert/test-expert",
+  "@create-expert/verify-test",
 ]
 
 [experts."create-expert".skills."@perstack/base"]
@@ -134,7 +156,7 @@ pick = ["readTextFile", "exec", "attemptCompletion"]
 
 [experts."@create-expert/plan"]
 defaultModelTier = "high"
-version = "1.0.20"
+version = "1.0.21"
 description = """
 Analyzes the user's request and produces plan.md: domain constraints, test query, verification signals, and role architecture.
 Provide: (1) what the expert should do, (2) path to existing perstack.toml if one exists.
@@ -218,74 +240,13 @@ pick = [
   "attemptCompletion",
 ]
 
-# =============================================================================
-# build — Write → Test → Verify Cycle Orchestrator
-# =============================================================================
-
-[experts."@create-expert/build"]
-defaultModelTier = "low"
-version = "1.0.20"
-description = """
-Orchestrates the write → review → test → verify cycle for perstack.toml.
-Provide: path to plan.md (containing requirements, architecture, test query, and verification signals).
-Optionally: path to existing perstack.toml to preserve.
-"""
-instruction = """
-You are the build loop orchestrator. You coordinate write-definition, review-definition, test-expert, and verify-test to produce a perstack.toml that passes both review and verification.
-
-You do NOT write perstack.toml yourself. You do NOT evaluate results yourself. You delegate to specialists and act on their verdicts.
-
-## Delegates
-
-- @create-expert/write-definition — writes or modifies perstack.toml from plan.md
-- @create-expert/review-definition — reviews perstack.toml against plan.md for domain alignment and instruction quality
-- @create-expert/test-expert — executes the test query against perstack.toml and reports what happened (no evaluation)
-- @create-expert/verify-test — executes hard signal checks, verifies their reproducibility, and checks the definition structure
-
-## Write → Review → Test → Verify Cycle
-
-1. Delegate to write-definition: pass plan.md path (and existing perstack.toml path if Update mode)
-2. Delegate to review-definition: pass plan.md path and perstack.toml path
-3. If review returns CONTINUE: delegate to write-definition with the review feedback, then restart from step 2
-4. If review returns PASS: delegate to test-expert with the test query from plan.md, perstack.toml path, and coordinator expert name (do NOT pass verification signals — test-expert is a pure executor)
-5. Delegate to verify-test: pass the test-expert result, the verification signals from plan.md, and the perstack.toml path
-6. If verify-test returns CONTINUE: validate the feedback (see below), then delegate to write-definition with actionable feedback, restart from step 2
-7. If verify-test returns PASS: done — attemptCompletion with the verification evidence
-
-### Validating CONTINUE feedback
-Before looping, check whether verify-test's feedback is a hard signal failure (command X → expected Y → got Z) or a soft opinion (content quality, style, implementation choices). Only hard signal failures and structural check failures are valid loop reasons. If verify-test reports issues that are not tied to a specific command result, do NOT loop — report the current state and note the discrepancy.
-
-### Maximum 3 iterations
-The write → review → test → verify cycle may run at most 3 times. If all signals have not passed after 3 iterations, attemptCompletion with: what passed, what failed, and the feedback from each iteration. Do NOT continue looping beyond this limit.
-
-### IMPORTANT: One delegate call per response
-Delegate to exactly ONE delegate per response. Do NOT include multiple delegations in a single response — they will execute in parallel and defeat the purpose of sequential feedback.
-
-### Guardrails
-- Do NOT delete perstack.toml — it is the final deliverable
-- attemptCompletion must include the full verification evidence from verify-test
-"""
-delegates = [
-  "@create-expert/write-definition",
-  "@create-expert/review-definition",
-  "@create-expert/test-expert",
-  "@create-expert/verify-test",
-]
-
-[experts."@create-expert/build".skills."@perstack/base"]
-type = "mcpStdioSkill"
-description = "File operations and task management"
-command = "npx"
-packageName = "@perstack/base"
-pick = ["readTextFile", "exec", "todo", "attemptCompletion"]
-
 # =============================================================================
 # write-definition — perstack.toml Author
 # =============================================================================
 
 [experts."@create-expert/write-definition"]
 defaultModelTier = "low"
-version = "1.0.20"
+version = "1.0.21"
 description = """
 Writes or modifies a perstack.toml definition from plan.md requirements and architecture.
 Provide: (1) path to plan.md, (2) optionally path to existing perstack.toml to preserve, (3) optionally feedback from a failed test to address.
@@ -388,7 +349,7 @@ pick = [
 
 [experts."@create-expert/review-definition"]
 defaultModelTier = "low"
-version = "1.0.20"
+version = "1.0.21"
 description = """
 Reviews perstack.toml against plan.md for domain knowledge alignment and instruction quality.
 Provide: (1) path to plan.md, (2) path to perstack.toml.
@@ -437,7 +398,7 @@ pick = ["readTextFile", "todo", "attemptCompletion"]
 
 [experts."@create-expert/verify-test"]
 defaultModelTier = "low"
-version = "1.0.20"
+version = "1.0.21"
 description = """
 Executes hard signal checks against test-expert's results, verifies their reproducibility, and checks the definition structure.
 Provide: (1) the test-expert's factual report (query, what was produced, errors), (2) the verification signals from plan.md, (3) path to perstack.toml.
@@ -502,7 +463,7 @@ pick = ["readTextFile", "exec", "todo", "attemptCompletion"]
 
 [experts."@create-expert/test-expert"]
 defaultModelTier = "low"
-version = "1.0.20"
+version = "1.0.21"
 description = """
 Executes a single test query against a Perstack expert definition and reports what happened.
 Provide: (1) path to perstack.toml, (2) the test query to execute, (3) the coordinator expert name to test.